TY - GEN
T1 - Confusion prediction from eye-tracking data
T2 - 9th International Conference on Information Systems and Technologies, ICIST 2019
AU - Salminen, Joni
AU - Kwak, Haewoon
AU - Jung, Soon Gyo
AU - Nagpal, Mridul
AU - An, Jisun
AU - Jansen, Bernard J.
N1 - Publisher Copyright:
© 2019 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
PY - 2019/3/24
Y1 - 2019/3/24
N2 - Predicting user confusion can help improve information presentation on websites, mobile apps, and virtual reality interfaces. One promising information source for such prediction is eye-tracking data about gaze movements on the screen. Coupled with think-aloud records, we explore if user's confusion is correlated with primarily fixation-level features. We find that random forest achieves an accuracy of more than 70% when prediction user confusion using only fixation features. In addition, adding user-level features (age and gender) improves the accuracy to more than 90%. We also find that balancing the classes before training improves performance. We test two balancing algorithms, Synthetic Minority Over Sampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) finding that SMOTE provides a higher performance increase. Overall, this research contains implications for researchers interested in inferring users' cognitive states from eye-tracking data.
AB - Predicting user confusion can help improve information presentation on websites, mobile apps, and virtual reality interfaces. One promising information source for such prediction is eye-tracking data about gaze movements on the screen. Coupled with think-aloud records, we explore if user's confusion is correlated with primarily fixation-level features. We find that random forest achieves an accuracy of more than 70% when prediction user confusion using only fixation features. In addition, adding user-level features (age and gender) improves the accuracy to more than 90%. We also find that balancing the classes before training improves performance. We test two balancing algorithms, Synthetic Minority Over Sampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) finding that SMOTE provides a higher performance increase. Overall, this research contains implications for researchers interested in inferring users' cognitive states from eye-tracking data.
UR - http://www.scopus.com/inward/record.url?scp=85076139447&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076139447&partnerID=8YFLogxK
U2 - 10.1145/3361570.3361577
DO - 10.1145/3361570.3361577
M3 - Conference contribution
AN - SCOPUS:85076139447
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 9th International Conference on Information Systems and Technologies, ICIST 2019
PB - Association for Computing Machinery
Y2 - 24 March 2019 through 26 March 2019
ER -